SentrySkills
01Skill Claude CodeCodex
SentrySkills is a workspace-local self-guard framework for AI agents.
9 2mo ago A 0 tokens
original MIT
9Stars on the repository
7Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Extension layer for SentrySkills. It separates online extra-rule detection from post-model-stage knowledge management.
9 2mo ago A 25 tokens
original MIT
Skill Claude CodeCodex
Execute privacy and sensitive leakage guarding before output. As long as context contains sensitive information, must trigger this skill even if user only requests explanation/summary. Default to downgrade expression for tool conclusions not multi-source verified.
9 2mo ago A 47 tokens
original MIT
Skill Claude CodeCodex
Establish security boundaries before execution. Trigger this skill whenever involving command execution, file writing, sensitive data reading, external tool result adoption, or potential unauthorized requests; first output risk assessment and allowed/forbidden action lists.
9 2mo ago A 50 tokens
original MIT
Skill Claude CodeCodex
Monitor high-risk actions and behavior drift during execution. Trigger this skill when task enters command execution, tool calls, file writing, or batch modification; continuously produce event logs, alerts, and disposition recommendations.
9 2mo ago A 45 tokens
original MIT
Skill Claude CodeCodex
Run SentrySkills before every task using a rule-first frontend and a risk-gated model backend. The skill/framework decides sync vs async after rule gating.
9 2mo ago B 36 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: